Hybridized Level Set Based Image Segmentation in UAV Images for Surveillance Applications

Image segmentation is one of the most difficult, dynamic and challenging problems in the image processing domain. It denotes a process by which a raw input image is partitioned into non-overlapping regions such that each region is homogeneous and the union of two adjacent regions is heterogeneous. This paper proposes a novel level set based method for image segmentation, which is able to deal with intensity inhomogeneities in the segmentation for UAV captured images. Level set algorithm is often used for region-based homogeneous image segmentation. When noisy, inhomogeneous image segmentation is required, Level set algorithm should be modified such that it can be less sensitive to noise and inhomogeneity in an image. In that context, our proposed method for noisy images, by hybridizing level set algorithm with superseding, is proposed. Experiments show that our method is more robust to initialization, faster and more accurate than the well-known other image segmentation model.